logic-whiteboard
Skill345 starsChanged 6 days agoMITView on GitHub
白板论证：把一篇文章的推理过程摊成一条纵向主干的长图——问题在上，前提、证据、矛盾、转折、分支逐层往下，停在内容自身的收束处；每段原文都必须进入某一步或写明省略理由（论证账本 + 来源清单校验）。输入是文章（原文、译文、逐字稿）。可以单独用，也可以接在抓取、视频转文字、翻译后面。Use when the user wants a 白板, 论证图, 推理过程图, 思路图, argument map, "把这篇的逻辑画出来", or -w.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- article2mediaSkill
- article-comicSkill
- article-fetchSkill
- article-rewriteSkill
- article-translateSkill
- explainer-videoSkill
- image-cardsSkill
- long-imageSkill
- video-transcriptSkill
- wechat-layoutSkill
The file
Files
白板论证（logic-whiteboard）
路径约定：文中的
${CLAUDE_SKILL_DIR}指本 SKILL.md 所在的目录。宿主没有替换这个变量时（命令里原样出现${CLAUDE_SKILL_DIR}），把它换成这个目录的绝对路径再运行；../<名字>/指同级的另一个 skill 目录。
呈现作者怎样一步步走到结论，不是摘要：读者只看成品，也应能复述"为什么下一步从上一步发生"。
参数：$ARGUMENTS
0. 输入
文章 article.md（原文、译文或逐字稿）。给的是链接、文件或视频时，先用 article-fetch / video-transcript 取原文（见 ../article2media/references/pipeline.md）。不需要先改写。
第一次使用先跑 node ${CLAUDE_SKILL_DIR}/scripts/doctor.mjs（Node 22+、Chrome）。
1. 流程
node ${CLAUDE_SKILL_DIR}/scripts/whiteboard.mjs <目录>/article.md：生成来源清单whiteboard-source.json（每段一个编号和哈希）。- 完整读一遍文章，读
references/mode-whiteboard.md，写<目录>/whiteboard.json（论证账本：每段原文必须进入某一步，或写明省略理由）。 whiteboard.mjs <目录>/whiteboard.json --check通过后，whiteboard.mjs <目录>/whiteboard.json渲染 →<目录>/whiteboard/whiteboard.png。- 讲概念、机制的内容，按
../article-rewrite/references/writing-guide.md第 6 节把具体情形、判别依据、关系和结果接起来。
2. 审片与交付
whiteboard/review/里有覆盖全部高度的重叠切片，逐张看完再交付。- 报告：PNG 路径与像素尺寸、来源、步骤数、可见转折数、来源段落的去向（几段进入步骤、几段省略及理由）。制作范围、是否核对过，写在交付回复里，不写进图里。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.